OpenClaw Enterprise
Open-source, vendor-neutral platform for managing persistent AI agents in sensitive, security-conscious environments.
Description
OpenClaw Enterprise (OCE) is an open-source, vendor-neutral platform for managing persistent AI agents in sensitive environments. It extends the OpenClaw project — a personal AI agent — toward team and organization-wide deployments.
The project originally started at OpenAI and was then donated to the OpenClaw Foundation; it has been further developed in collaboration with Red Hat and NVIDIA. OCE is being piloted internally at companies like Red Hat and OpenAI.
The platform combines hard boundaries between trusted and untrusted workloads with sandboxing, LLM-based reviews, and fine-grained permissions. It provides multi-tenancy support, standardized agentic primitives, and governance and auditability across the agent lifecycle. Core primitives — the harness, model, and sandbox — can be swapped out with third-party solutions.
Deployment is self-hosted: docker-compose for local development and Kubernetes for internal deployments. The software is free and, per its maintainers, will always remain free. Version 1.0 is planned for later in 2026.